All

Papers

Browse and search HCI research papers from All

Active Filters

Author: 10564

12 results

The Shape of My-AI: How Multimodality Shapes Trust and Persuasion in Interactions with an AI-Generated Future Self

AI-generated future selves allow people to engage in dialogue with a personalized digital representation of themselves decades ahead, yet it remains unclear how presentation modality shapes their psychological impact. We report a randomized between-subjects study (n=92) comparing three modalities of an AI-generated fu…

Constanze Albrecht et al.Massachusetts Institute of Technology

Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI

Millions of users now design personalized LLM-based chatbots through system prompts that shape their daily interactions, yet have limited ability to anticipate how these design choices will manifest as behaviors in deployment. This opacity is consequential: seemingly innocuous prompts can trigger excessive sycophancy,…

Sheer Karny et al.Massachusetts Institute of Technology

OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change

Marine ecosystems face unprecedented threats from climate change and plastic pollution, yet traditional environmental education often struggles to translate awareness into meaningful actions. This paper presents OceanChat, an interactive system leveraging large language models to create conversational AI agents repres…

Pat Pataranutaporn et al.Massachusetts Institute of Technology

Personal Validation Effect in LLMs: Positive AI Responses Bias Perceptions of Validity, Reliability, Personalization, and Usefulness of Fictitious Predictions

Large Language Models (LLMs) are becoming increasingly ubiquitous in daily life, impacting decision-making across various domains. A substantial body of prior work has shown that individuals tend to evaluate positive predictions more favorably than negative ones---a phenomenon often referred to as the personal validat…

Pat Pataranutaporn et al.Massachusetts Institute of Technology

AdRecommended

Learn AI Coding at CodeNow

Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work.

Explore Now

From Synthetic to Human: The Gap Between AI-Predicted and Actual Pro-Environmental Behavior Change After Chatbot Persuasion

Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive. We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,600 participants: real humans (n=1,200), simulated humans based on actual participant dat…

Alexander Doudkin et al.

MIT Media Lab

Slip Through the Chat: Subtle Injection of False Information in LLM Chatbot Conversation Increases False Memory Formation

This study examines the potential for malicious generative chatbots to induce false memories by injecting subtle misinformation during user interactions. An experiment involving 180 participants explored five intervention conditions following the presentation of an article: (1) no intervention, (2) reading an honest o…

Pat Pataranutaporn et al.Massachusetts Institute of Technology

Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest Explanations

Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and discredit true information. We examined the impact of deceptive AI generated explanatio…

Valdemar Danry et al.Massachusetts Institute of Technology

Synthetic Human Memories: AI-Edited Images and Videos Can Implant False Memories and Distort Recollection

AI is increasingly used to enhance images and videos, both intentionally and unintentionally. As AI editing tools become more integrated into smartphones, users can modify or animate photos into realistic videos. This study examines the impact of AI-altered visuals on false memories—recollections of events that didn’t…

Pat Pataranutaporn et al.Massachusetts Institute of Technology

Talk to the Hand: an LLM-powered Chatbot with Visual Pointer as Proactive Companion for On-Screen Tasks

This paper presents Pointer Assistant, a novel human-AI interaction technique for on-screen tasks. The design features a chatbot displayed as an extra mouse pointer, alongside the user's, which proactively gives feedback on user actions while directing them to relevant areas on the screen and responding to the user's…

Thanawit Prasongpongchai et al.KASIKORN

Putting Things into Context: Generative AI-Enabled Context Personalization for Vocabulary Learning Improves Learning Motivation

Fostering students' interests in learning is considered to have many positive downstream effects. Large language models have opened up new horizons for generating content tuned to one's interests, yet it is unclear in what ways and to what extent this customization could have positive effects on learning. To explore t…

Joanne Leong et al.Massachusetts Institute of Technology

AI Comes Out of the Closet: Using AI-Generated Virtual Characters to Help Individuals Practice LGBTQIA+ Advocacy

Despite significant historical progress, discrimination and social stigma continue to impact the lives of LGBTQIA+ individuals. The use of AI-generated virtual characters offers a unique opportunity to facilitate advocacy by engaging individuals in simulated conversations that can foster understanding, education, and…

Daniel Pillis et al.Massachusetts Institute of Technology

Don’t Just Tell Me, Ask Me: AI Systems that Intelligently Frame Explanations as Questions Improve Human Logical Discernment Accuracy over Causal AI explanations

Critical thinking is an essential human skill. Despite the importance of critical thinking, research reveals that our reasoning ability suffers from personal biases and cognitive resource limitations, leading to potentially dangerous outcomes. This paper presents the novel idea of AI-framed Questioning that turns info…

Valdemar Danry et al.Massachusetts Institute of Technology

Paper Title	Authors	Research Topics	Paper Database	Year
The Shape of My-AI: How Multimodality Shapes Trust and Persuasion in Interactions with an AI-Generated Future Self AI-generated future selves allow people to engage in dialogue with a personalized digital representation of themselves decades ahead, yet it remains unclear how presentation modality shapes their psychological impact. We report a randomized between-subjects study (n=92) comparing three modalities of an AI-generated fu…	CA Constanze Albrecht et al.Massachusetts Institute of Technology
Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI Millions of users now design personalized LLM-based chatbots through system prompts that shape their daily interactions, yet have limited ability to anticipate how these design choices will manifest as behaviors in deployment. This opacity is consequential: seemingly innocuous prompts can trigger excessive sycophancy,…	SK Sheer Karny et al.Massachusetts Institute of Technology
OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change Marine ecosystems face unprecedented threats from climate change and plastic pollution, yet traditional environmental education often struggles to translate awareness into meaningful actions. This paper presents OceanChat, an interactive system leveraging large language models to create conversational AI agents repres…	PP Pat Pataranutaporn et al.Massachusetts Institute of Technology
Personal Validation Effect in LLMs: Positive AI Responses Bias Perceptions of Validity, Reliability, Personalization, and Usefulness of Fictitious Predictions Large Language Models (LLMs) are becoming increasingly ubiquitous in daily life, impacting decision-making across various domains. A substantial body of prior work has shown that individuals tend to evaluate positive predictions more favorably than negative ones---a phenomenon often referred to as the personal validat…	PP Pat Pataranutaporn et al.Massachusetts Institute of Technology
AdRecommended Learn AI Coding at CodeNow Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work. Explore Now
From Synthetic to Human: The Gap Between AI-Predicted and Actual Pro-Environmental Behavior Change After Chatbot Persuasion Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive. We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,600 participants: real humans (n=1,200), simulated humans based on actual participant dat…	AD Alexander Doudkin et al.MIT Media Lab
Slip Through the Chat: Subtle Injection of False Information in LLM Chatbot Conversation Increases False Memory Formation This study examines the potential for malicious generative chatbots to induce false memories by injecting subtle misinformation during user interactions. An experiment involving 180 participants explored five intervention conditions following the presentation of an article: (1) no intervention, (2) reading an honest o…	PP Pat Pataranutaporn et al.Massachusetts Institute of Technology
emoji_events Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest Explanations Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and discredit true information. We examined the impact of deceptive AI generated explanatio…	VD Valdemar Danry et al.Massachusetts Institute of Technology
emoji_events Synthetic Human Memories: AI-Edited Images and Videos Can Implant False Memories and Distort Recollection AI is increasingly used to enhance images and videos, both intentionally and unintentionally. As AI editing tools become more integrated into smartphones, users can modify or animate photos into realistic videos. This study examines the impact of AI-altered visuals on false memories—recollections of events that didn’t…	PP Pat Pataranutaporn et al.Massachusetts Institute of Technology
Talk to the Hand: an LLM-powered Chatbot with Visual Pointer as Proactive Companion for On-Screen Tasks This paper presents Pointer Assistant, a novel human-AI interaction technique for on-screen tasks. The design features a chatbot displayed as an extra mouse pointer, alongside the user's, which proactively gives feedback on user actions while directing them to relevant areas on the screen and responding to the user's…	TP Thanawit Prasongpongchai et al.KASIKORN
Putting Things into Context: Generative AI-Enabled Context Personalization for Vocabulary Learning Improves Learning Motivation Fostering students' interests in learning is considered to have many positive downstream effects. Large language models have opened up new horizons for generating content tuned to one's interests, yet it is unclear in what ways and to what extent this customization could have positive effects on learning. To explore t…	JL Joanne Leong et al.Massachusetts Institute of Technology
AI Comes Out of the Closet: Using AI-Generated Virtual Characters to Help Individuals Practice LGBTQIA+ Advocacy Despite significant historical progress, discrimination and social stigma continue to impact the lives of LGBTQIA+ individuals. The use of AI-generated virtual characters offers a unique opportunity to facilitate advocacy by engaging individuals in simulated conversations that can foster understanding, education, and…	DP Daniel Pillis et al.Massachusetts Institute of Technology
Don’t Just Tell Me, Ask Me: AI Systems that Intelligently Frame Explanations as Questions Improve Human Logical Discernment Accuracy over Causal AI explanations Critical thinking is an essential human skill. Despite the importance of critical thinking, research reveals that our reasoning ability suffers from personal biases and cognitive resource limitations, leading to potentially dangerous outcomes. This paper presents the novel idea of AI-framed Questioning that turns info…	VD Valdemar Danry et al.Massachusetts Institute of Technology